Skip to content

aiskillstore/marketplace / skills/aaron-he-zhu/memory-management

memory-management

Verified

Use when the user asks to "remember project context", review saved findings, initialize runtime memory, archive stale work, reconcile notes, or erase a subject; manages authorized HOT/WARM/COLD working memory across all disciplines while preserving registry event ownership and privacy controls. Not for changing canonical registry facts - route those through the owning registry. 项目记忆/跨会话

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-27T11:27:20.123Z",
    "slug": "aaron-he-zhu-memory-management",
    "source_url": "https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/protocol/memory-management",
    "source_ref": "main",
    "model": "claude",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "fdcb3fd6cbdbc40a48054ce2f496ca5f6c680c0b95c2d7184146a07000ff8bc5",
    "tree_hash": "fe0d6717847c97ba4a9972643186b36b835d41768d5da9cfe06bee1e92bd5523",
    "provenance": {
      "model_effective": "claude",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "failed",
          "error": "2026-07-27T11:27:20.227369Z ERROR codex_models_manager::manager: failed to refresh available models: Missing environment variable: `HELM_API_KEY`.\n2026-07-27T11:27:20.255356Z ERROR codex_models_manage…"
        },
        {
          "agent": "claude",
          "outcome": "failed",
          "error": "Unknown error"
        },
        {
          "agent": "codex",
          "outcome": "failed",
          "error": "2026-07-27T11:27:51.463289Z ERROR codex_models_manager::manager: failed to refresh available models: Missing environment variable: `HELM_API_KEY`.\n2026-07-27T11:27:51.481695Z ERROR codex_models_manage…"
        },
        {
          "agent": "claude",
          "outcome": "failed",
          "error": "Unknown error"
        },
        {
          "agent": "codex",
          "outcome": "failed",
          "error": "2026-07-27T11:28:19.231604Z ERROR codex_models_manager::manager: failed to refresh available models: Missing environment variable: `HELM_API_KEY`.\n2026-07-27T11:28:19.251785Z ERROR codex_models_manage…"
        },
        {
          "agent": "claude",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    },
    "upstream_version_raw": "19.0.0",
    "upstream_version_normalized": "19.0.0",
    "upstream_version_source": "metadata.version",
    "upstream_version_status": "not_bumped",
    "upstream_commit_sha": "872fb912bb0b55629302d813e22b01895c09c809"
  },
  "skill": {
    "name": "memory-management",
    "description": "Manage authorized project working memory across HOT, WARM, and COLD notes, with privacy controls and registry ownership boundaries.",
    "summary": "Manage authorized project memory without changing canonical registry facts.",
    "icon": "📦",
    "version": "19.0.0",
    "author": "aaron-he-zhu",
    "license": "Apache-2.0",
    "tags": [
      "project-memory",
      "context-management",
      "privacy",
      "knowledge-management",
      "claude-code"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "filesystem",
      "network"
    ],
    "category": "productivity"
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "Three documented local Python commands are confirmed as external-command actions for initialization, consent lookup, and artifact validation. The remaining 34 detections are false positives from Markdown formatting, fixed documentation links, metadata URLs, and a redirected git error stream. No prompt injection, data exfiltration intent, or malicious behavior was found in the reviewed content.",
    "remediation": [
      {
        "issue": "Local Python scripts are executed from a resolved repository root.",
        "suggestion": "Require an explicit confirmation immediately before each write-capable command, validate the resolved root, and document the expected script checksum or trusted installation source.",
        "severity": "medium"
      },
      {
        "issue": "The consent lookup command accepts an aggregate identifier placeholder.",
        "suggestion": "Pass identifiers as a separately quoted argument, validate the accepted identifier format, and avoid placing sensitive identifiers in command history or logs.",
        "severity": "medium"
      },
      {
        "issue": "Privacy procedures discuss working-tree deletion and history erasure.",
        "suggestion": "Keep dry-run and scope confirmation mandatory, require a protected backup process, and clearly separate routine working-tree erasure from administrator-approved history rewriting.",
        "severity": "medium"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "references/examples.md",
            "line_start": 50,
            "line_end": 51
          },
          {
            "file": "SKILL.md",
            "line_start": 22,
            "line_end": 28
          },
          {
            "file": "SKILL.md",
            "line_start": 28,
            "line_end": 34
          },
          {
            "file": "SKILL.md",
            "line_start": 34,
            "line_end": 34
          },
          {
            "file": "SKILL.md",
            "line_start": 67,
            "line_end": 67
          },
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 68
          },
          {
            "file": "SKILL.md",
            "line_start": 69,
            "line_end": 69
          },
          {
            "file": "SKILL.md",
            "line_start": 74,
            "line_end": 75
          },
          {
            "file": "SKILL.md",
            "line_start": 75,
            "line_end": 86
          },
          {
            "file": "SKILL.md",
            "line_start": 86,
            "line_end": 86
          },
          {
            "file": "SKILL.md",
            "line_start": 87,
            "line_end": 88
          },
          {
            "file": "SKILL.md",
            "line_start": 88,
            "line_end": 88
          },
          {
            "file": "SKILL.md",
            "line_start": 89,
            "line_end": 89
          },
          {
            "file": "SKILL.md",
            "line_start": 94,
            "line_end": 94
          },
          {
            "file": "SKILL.md",
            "line_start": 101,
            "line_end": 102
          },
          {
            "file": "SKILL.md",
            "line_start": 102,
            "line_end": 108
          },
          {
            "file": "SKILL.md",
            "line_start": 108,
            "line_end": 108
          },
          {
            "file": "SKILL.md",
            "line_start": 112,
            "line_end": 115
          },
          {
            "file": "SKILL.md",
            "line_start": 115,
            "line_end": 116
          },
          {
            "file": "SKILL.md",
            "line_start": 116,
            "line_end": 116
          },
          {
            "file": "SKILL.md",
            "line_start": 118,
            "line_end": 118
          },
          {
            "file": "SKILL.md",
            "line_start": 125,
            "line_end": 149
          },
          {
            "file": "SKILL.md",
            "line_start": 149,
            "line_end": 149
          },
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 68
          },
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 68
          }
        ]
      },
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "references/gdpr-purge-log-template.md",
            "line_start": 48,
            "line_end": 48
          },
          {
            "file": "references/gdpr-purge-log-template.md",
            "line_start": 49,
            "line_end": 49
          },
          {
            "file": "SKILL.md",
            "line_start": 32,
            "line_end": 32
          },
          {
            "file": "SKILL.md",
            "line_start": 51,
            "line_end": 51
          },
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 68
          },
          {
            "file": "SKILL.md",
            "line_start": 140,
            "line_end": 140
          },
          {
            "file": "SKILL.md",
            "line_start": 141,
            "line_end": 141
          },
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 68
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 10,
            "line_end": 10
          },
          {
            "file": "SKILL.md",
            "line_start": 13,
            "line_end": 13
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:references/examples.md:50:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "references/examples.md",
        "line_start": 50,
        "line_end": 51,
        "snippet": "Current list stored in: `memory/research/keywords/long-tail-keywords.md` (tagged \"quick-win\")"
      },
      {
        "id": "blocker:references/examples.md:90:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/examples.md",
        "line_start": 90,
        "line_end": 90,
        "snippet": "- **Concurrent access**: Use timestamped filenames to avoid overwrites from parallel sessions."
      },
      {
        "id": "filesystem:references/gdpr-purge-log-template.md:48:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "references/gdpr-purge-log-template.md",
        "line_start": 48,
        "line_end": 48,
        "snippet": "- [memory-management SKILL.md §GDPR / Privacy Compliance](../SKILL.md) — purge procedure and its hon"
      },
      {
        "id": "filesystem:references/gdpr-purge-log-template.md:49:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "references/gdpr-purge-log-template.md",
        "line_start": 49,
        "line_end": 49,
        "snippet": "- [references/skill-contract.md](../../../references/skill-contract.md) — Write Paths table"
      },
      {
        "id": "blocker:references/update-triggers-integration.md:20:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/update-triggers-integration.md",
        "line_start": 20,
        "line_end": 20,
        "snippet": "| Paid readback | Save normalized window and truth-set reconciliation | Claim/offer proposal when st"
      },
      {
        "id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 22,
        "line_end": 28,
        "snippet": "```text"
      },
      {
        "id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 28,
        "line_end": 34,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 34,
        "line_end": 34,
        "snippet": "Operational `memory/**` is Git-ignored by default. Initialize from `memory/templates/`; never commit"
      },
      {
        "id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 67,
        "line_end": 67,
        "snippet": "1. Copy the minimal safe starters from `memory/templates/` into runtime `memory/` only after authori"
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 68,
        "line_end": 68,
        "snippet": "2. Read [`runtime-invocation.md`](../../references/runtime-invocation.md), resolve `AARON_SKILLS_ROO"
      },
      {
        "id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 69,
        "line_end": 69,
        "snippet": "3. Confirm `.gitignore` excludes runtime memory and `git status --ignored` shows it as ignored."
      },
      {
        "id": "external_commands:SKILL.md:74:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 74,
        "line_end": 75,
        "snippet": "1. Check live consent with `python3 \"$AARON_SKILLS_ROOT/scripts/registry-events.py\" is-suppressed <a"
      },
      {
        "id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 75,
        "line_end": 86,
        "snippet": "2. Query the relevant registry projection and record its `last_offset`/revision."
      },
      {
        "id": "external_commands:SKILL.md:86:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 86,
        "line_end": 86,
        "snippet": "- Refresh `memory/session-checkpoint.md` after each completed skill handoff (template: `memory/templ"
      },
      {
        "id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 87,
        "line_end": 88,
        "snippet": "- Non-owner skills submit durable truth as `operation: propose` to the relevant event stream. They d"
      },
      {
        "id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 88,
        "line_end": 88,
        "snippet": "- Only a host-capability registry-owner principal may accept/reject a proposal or issue an owner `up"
      },
      {
        "id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 89,
        "line_end": 89,
        "snippet": "- `memory/decisions.md` entries require `approved_by: user`, an approval reference, and date. Inferr"
      },
      {
        "id": "external_commands:SKILL.md:94:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 94,
        "line_end": 94,
        "snippet": "- WARM files older than 90 days by `last_updated` are candidates for COLD archival with a `YYYY-MM-D"
      },
      {
        "id": "external_commands:SKILL.md:101:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 101,
        "line_end": 102,
        "snippet": "2. Preserve conflicts. Mark the older note `superseded_by` only when newer evidence is comparable an"
      },
      {
        "id": "external_commands:SKILL.md:102:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 102,
        "line_end": 108,
        "snippet": "3. For registry-owned facts, create a proposal with current `expected_revision`; do not edit the vie"
      },
      {
        "id": "external_commands:SKILL.md:108:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 108,
        "line_end": 108,
        "snippet": "Auditor outputs are written only after explicit authorization and must pass `python3 \"$AARON_SKILLS_"
      },
      {
        "id": "external_commands:SKILL.md:112:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 112,
        "line_end": 115,
        "snippet": "Use `memory-management purge <pseudonymous-aggregate-id>` only with explicit user or data-subject au"
      },
      {
        "id": "external_commands:SKILL.md:115:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 115,
        "line_end": 116,
        "snippet": "2. Apply an immediate consent `suppress` event first when communications may be involved. Confirm su"
      },
      {
        "id": "external_commands:SKILL.md:116:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 116,
        "line_end": 116,
        "snippet": "3. Delete or anonymize authorized working notes and rendered views. For each affected registry, a ho"
      },
      {
        "id": "external_commands:SKILL.md:118:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 118,
        "line_end": 118,
        "snippet": "5. Append a subject-minimized operation record to `memory/privacy/erasure-log.md`; this operational "
      },
      {
        "id": "external_commands:SKILL.md:125:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 125,
        "line_end": 149,
        "snippet": "`hooks/claude-hook.sh` currently:"
      },
      {
        "id": "external_commands:SKILL.md:149:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 149,
        "line_end": 149,
        "snippet": "Route a canonical conflict to its owner: `entity-registry`, `creator-registry`, `offer-claims-regist"
      },
      {
        "id": "external_commands:SKILL.md:68:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "SKILL.md",
        "line_start": 68,
        "line_end": 68,
        "snippet": "2. Read [`runtime-invocation.md`](../../references/runtime-invocation.md), resolve `AARON_SKILLS_ROO"
      },
      {
        "id": "external_commands:SKILL.md:68:template-literal-with-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Template literal with command substitution",
        "file": "SKILL.md",
        "line_start": 68,
        "line_end": 68,
        "snippet": "2. Read [`runtime-invocation.md`](../../references/runtime-invocation.md), resolve `AARON_SKILLS_ROO"
      },
      {
        "id": "network:SKILL.md:10:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 10,
        "line_end": 10,
        "snippet": "homepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\""
      },
      {
        "id": "network:SKILL.md:13:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 13,
        "line_end": 13,
        "snippet": "metadata: {\"author\": \"aaron-he-zhu\", \"version\": \"19.0.0\", \"discipline\": \"protocol\", \"phase\": \"protoc"
      },
      {
        "id": "filesystem:SKILL.md:32:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 32,
        "line_end": 32,
        "snippet": "**Reads:** authorized runtime memory, registry projections/events, approved decisions, and [state-mo"
      },
      {
        "id": "filesystem:SKILL.md:51:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 51,
        "line_end": 51,
        "snippet": "Use [skill-contract.md](../../references/skill-contract.md). Include authorization status, changed p"
      },
      {
        "id": "filesystem:SKILL.md:68:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 68,
        "line_end": 68,
        "snippet": "2. Read [`runtime-invocation.md`](../../references/runtime-invocation.md), resolve `AARON_SKILLS_ROO"
      },
      {
        "id": "filesystem:SKILL.md:140:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 140,
        "line_end": 140,
        "snippet": "- [State model](../../references/state-model.md)"
      },
      {
        "id": "filesystem:SKILL.md:141:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 141,
        "line_end": 141,
        "snippet": "- [Registry event protocol](../../references/registry-event-protocol.md)"
      },
      {
        "id": "filesystem:SKILL.md:68:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "SKILL.md",
        "line_start": 68,
        "line_end": 68,
        "snippet": "2. Read [`runtime-invocation.md`](../../references/runtime-invocation.md), resolve `AARON_SKILLS_ROO"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:references/examples.md:50:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks format a Markdown file path in a documentation example. They do not invoke a shell or execute Ruby."
      },
      {
        "id": "blocker:references/examples.md:90:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is advice about avoiding concurrent-file overwrites with timestamped filenames. It performs no system reconnaissance."
      },
      {
        "id": "filesystem:references/gdpr-purge-log-template.md:48:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The relative path is a Markdown cross-reference to the local SKILL.md file. It is not used for filesystem access."
      },
      {
        "id": "filesystem:references/gdpr-purge-log-template.md:49:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The relative path is a Markdown cross-reference to a repository reference document. It is not an untrusted path traversal operation."
      },
      {
        "id": "blocker:references/update-triggers-integration.md:20:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The line describes a paid readback workflow in a table. It contains no host inspection or reconnaissance instruction."
      },
      {
        "id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The fenced text block presents natural-language example requests. It does not contain shell or Ruby execution."
      },
      {
        "id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is the closing delimiter of a Markdown code fence, not a command execution construct."
      },
      {
        "id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Backticks only format repository paths and an ignore pattern in documentation. No shell is invoked."
      },
      {
        "id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks format local directory names in an authorization-gated initialization instruction. They do not execute code."
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.86,
        "reason": "The installation instructions execute git and a local Python registry script. Although intended for local initialization, execution changes local registry directories and requires user authorization and script integrity verification."
      },
      {
        "id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The line documents a git status command for manual verification. It does not interpolate user input or perform destructive actions."
      },
      {
        "id": "external_commands:SKILL.md:74:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.83,
        "reason": "The query procedure executes a local Python registry script using an aggregate identifier. It is an external command with privacy-sensitive lookup behavior, even though the procedure limits it to consent checks."
      },
      {
        "id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Backticks format a registry field name. The line has no shell command."
      },
      {
        "id": "external_commands:SKILL.md:86:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This line formats local filenames and size limits with Markdown backticks. It does not execute them."
      },
      {
        "id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The text uses backticks to name a structured operation value. It does not run an external command."
      },
      {
        "id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The text uses backticks to name structured operation values. It does not run an external command."
      },
      {
        "id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks identify a local file and field name in policy documentation. They are not executable syntax."
      },
      {
        "id": "external_commands:SKILL.md:94:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks format a metadata field and filename prefix. No command execution is present."
      },
      {
        "id": "external_commands:SKILL.md:101:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks format a metadata field name in consolidation guidance. No shell command is present."
      },
      {
        "id": "external_commands:SKILL.md:102:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks format a field name and local resources in documentation. No code executes."
      },
      {
        "id": "external_commands:SKILL.md:108:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.84,
        "reason": "The audit procedure executes a local validation script on an artifact path. This is a genuine external-command action and relies on the referenced script and runtime-root preflight."
      },
      {
        "id": "external_commands:SKILL.md:112:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks format a documented skill invocation and placeholder. This is not shell execution."
      },
      {
        "id": "external_commands:SKILL.md:115:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks label a structured consent event. They do not invoke a command."
      },
      {
        "id": "external_commands:SKILL.md:116:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks label structured operation values in a privacy procedure. They are not executable."
      },
      {
        "id": "external_commands:SKILL.md:118:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks format a local log path. No external command is executed."
      },
      {
        "id": "external_commands:SKILL.md:125:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks format the hook filename in a descriptive section. They do not execute the hook."
      },
      {
        "id": "external_commands:SKILL.md:149:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks name registry skills as routing targets. The text has no command execution."
      },
      {
        "id": "external_commands:SKILL.md:68:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.78,
        "reason": "The documented shell expansion resolves a repository root before running a local script. Its fallback is true and no untrusted value is inserted into the substitution."
      },
      {
        "id": "external_commands:SKILL.md:68:template-literal-with-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.78,
        "reason": "This is shell parameter expansion and command substitution in a documented local setup command, not a JavaScript template literal or remote execution."
      },
      {
        "id": "network:SKILL.md:10:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The URL is homepage metadata for the source repository. It is not fetched or used to transmit data."
      },
      {
        "id": "network:SKILL.md:13:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The URL is homepage metadata inside a local metadata object. No network request is specified."
      },
      {
        "id": "filesystem:SKILL.md:32:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The relative path is a Markdown link to a repository reference. It is not processed as an input path."
      },
      {
        "id": "filesystem:SKILL.md:51:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The relative path is a Markdown link to local documentation. It is not used for filesystem traversal."
      },
      {
        "id": "filesystem:SKILL.md:68:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The relative path is a fixed Markdown link to local invocation documentation. It is not user-controlled traversal."
      },
      {
        "id": "filesystem:SKILL.md:140:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is a fixed Markdown reference link, not a filesystem operation."
      },
      {
        "id": "filesystem:SKILL.md:141:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This is a fixed Markdown reference link, not a filesystem operation."
      },
      {
        "id": "filesystem:SKILL.md:68:standard-device-file-access",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The snippet uses shell redirection only to suppress git error output during root discovery. It does not access a device file for data collection."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [
      {
        "title": "Ruby/shell backtick execution",
        "description": "2. Read [`runtime-invocation.md`](../../references/runtime-invocation.md), resolve `AARON_SKILLS_ROO",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 68
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.86,
        "confidence_reasoning": "The installation instructions execute git and a local Python registry script. Although intended for local initialization, execution changes local registry directories and requires user authorization and script integrity verification."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "1. Check live consent with `python3 \"$AARON_SKILLS_ROOT/scripts/registry-events.py\" is-suppressed <a",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 74,
            "line_end": 75
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.83,
        "confidence_reasoning": "The query procedure executes a local Python registry script using an aggregate identifier. It is an external command with privacy-sensitive lookup behavior, even though the procedure limits it to consent checks."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "Auditor outputs are written only after explicit authorization and must pass `python3 \"$AARON_SKILLS_",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 108,
            "line_end": 108
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.84,
        "confidence_reasoning": "The audit procedure executes a local validation script on an artifact path. This is a genuine external-command action and relies on the referenced script and runtime-root preflight."
      }
    ],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 8,
    "total_lines": 537,
    "audit_model": "claude",
    "audited_at": "2026-07-27T11:27:20.123Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Organize Project Memory Safely",
    "value_statement": "Project context becomes difficult to find when notes are scattered or stale. This skill organizes authorized working memory while preserving registry ownership and privacy boundaries.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "project memory management",
      "context management",
      "working memory",
      "knowledge management",
      "privacy controls",
      "HOT WARM COLD notes",
      "session handoff"
    ],
    "actual_capabilities": [
      "Initialize private runtime memory from repository templates after authorization.",
      "Review HOT, WARM, and COLD notes with source and freshness guidance.",
      "Consolidate duplicate non-canonical notes while preserving conflicts and provenance.",
      "Archive stale working notes with path, hash, and supersession metadata.",
      "Prepare authorized privacy erasure work with dry-run scope reporting.",
      "Create handoff checkpoints without changing canonical registry facts."
    ],
    "limitations": [
      "It does not accept, reject, or directly change canonical registry facts.",
      "Persistent writes and purge operations require explicit authorization.",
      "It cannot prove complete erasure from Git history, backups, or external systems.",
      "It depends on project-local templates, registries, and validation scripts."
    ],
    "use_cases": [
      {
        "title": "Start a new project memory space",
        "description": "Initialize private memory templates and define the first priorities without storing sensitive production data.",
        "target_user": "Project manager"
      },
      {
        "title": "Prepare a cross-session handoff",
        "description": "Refresh a compact checkpoint with pending work, source offsets, and the next approved action.",
        "target_user": "Developer using an AI coding assistant"
      },
      {
        "title": "Review an erasure request",
        "description": "Plan a scoped privacy purge, identify affected working notes, and report limitations before any authorized deletion.",
        "target_user": "Privacy operations coordinator"
      }
    ],
    "prompt_templates": [
      {
        "title": "Initialize memory",
        "scenario": "Beginner",
        "prompt": "Initialize private project memory from the templates. Show the proposed paths and ask for approval before writing."
      },
      {
        "title": "Review current context",
        "scenario": "Intermediate",
        "prompt": "Review our HOT and WARM memory. List current priorities, stale notes, and the source record for each conclusion."
      },
      {
        "title": "Consolidate duplicates",
        "scenario": "Advanced",
        "prompt": "Find duplicate non-canonical notes for this campaign. Propose a consolidation plan that preserves conflicts and source references."
      },
      {
        "title": "Plan a privacy purge",
        "scenario": "Expert",
        "prompt": "Create a dry-run plan to erase the pseudonymous subject ID Subject-A1B2 from authorized working memory. Show scope and request confirmation before changes."
      }
    ],
    "output_examples": [
      {
        "input": "Review project memory for stale context.",
        "output": [
          "HOT: 4 active priorities with source pointers.",
          "WARM: 2 notes are older than 90 days and need review.",
          "No writes made."
        ]
      },
      {
        "input": "Prepare a consolidation plan for duplicate notes.",
        "output": [
          "Two non-canonical notes cover the same observation window.",
          "Keep the newer note as primary and retain the older note with a supersession reference.",
          "Registry-owned facts remain unchanged."
        ]
      }
    ],
    "best_practices": [
      "Ask for explicit approval before the first persistent write.",
      "Store source references and observation dates with every durable note.",
      "Treat HOT memory as an index and verify important facts in live registry records."
    ],
    "anti_patterns": [
      "Do not store credentials, raw contact data, or production exports in templates.",
      "Do not treat cached notes as proof of current consent or canonical truth.",
      "Do not delete ambiguous records without a confirmed scope and authority."
    ],
    "faq": [
      {
        "question": "Does this skill replace a project database?",
        "answer": "No. It manages working notes and pointers. Registry event streams remain the canonical source of facts."
      },
      {
        "question": "Can it write memory automatically?",
        "answer": "Only when the current request explicitly authorizes the persistent write. Read-only review and dry runs need no write approval."
      },
      {
        "question": "What are HOT, WARM, and COLD notes?",
        "answer": "HOT holds small current pointers, WARM holds active evidence, and COLD holds older historical material."
      },
      {
        "question": "Can it delete personal data?",
        "answer": "It can plan and perform authorized working-memory erasure. It cannot guarantee deletion from history, backups, or external systems."
      },
      {
        "question": "Does it change registry facts?",
        "answer": "No. It routes conflicts and proposed changes to the registry owner."
      },
      {
        "question": "Which AI tools can use this skill?",
        "answer": "The package declares compatibility with Claude, Codex, and Claude Code compatible hosts."
      }
    ]
  },
  "file_structure": [
    {
      "name": "references",
      "type": "dir",
      "path": "references",
      "children": [
        {
          "name": "consolidation-pass.md",
          "type": "file",
          "path": "references/consolidation-pass.md",
          "lines": 34
        },
        {
          "name": "examples.md",
          "type": "file",
          "path": "references/examples.md",
          "lines": 116
        },
        {
          "name": "gdpr-purge-log-template.md",
          "type": "file",
          "path": "references/gdpr-purge-log-template.md",
          "lines": 50
        },
        {
          "name": "glossary-template.md",
          "type": "file",
          "path": "references/glossary-template.md",
          "lines": 47
        },
        {
          "name": "hot-cache-template.md",
          "type": "file",
          "path": "references/hot-cache-template.md",
          "lines": 60
        },
        {
          "name": "promotion-demotion-rules.md",
          "type": "file",
          "path": "references/promotion-demotion-rules.md",
          "lines": 28
        },
        {
          "name": "update-triggers-integration.md",
          "type": "file",
          "path": "references/update-triggers-integration.md",
          "lines": 52
        }
      ]
    },
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 150
    }
  ]
}
receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 322kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 322kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 322kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 322kUpdated Claude CodeCodexVerifiedInstall